Text Generation
Transformers
Safetensors
English
Chinese
llama
minicpm
minicpm5
long-context
tool-calling
on-device
edge-ai
heretic
uncensored
decensored
abliterated
reproducible
conversational
text-generation-inference
Instructions to use YourIdentity/MiniCPM5-2B-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use YourIdentity/MiniCPM5-2B-heretic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="YourIdentity/MiniCPM5-2B-heretic") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("YourIdentity/MiniCPM5-2B-heretic") model = AutoModelForCausalLM.from_pretrained("YourIdentity/MiniCPM5-2B-heretic", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use YourIdentity/MiniCPM5-2B-heretic with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "YourIdentity/MiniCPM5-2B-heretic" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "YourIdentity/MiniCPM5-2B-heretic", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/YourIdentity/MiniCPM5-2B-heretic
- SGLang
How to use YourIdentity/MiniCPM5-2B-heretic with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "YourIdentity/MiniCPM5-2B-heretic" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "YourIdentity/MiniCPM5-2B-heretic", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "YourIdentity/MiniCPM5-2B-heretic" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "YourIdentity/MiniCPM5-2B-heretic", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use YourIdentity/MiniCPM5-2B-heretic with Docker Model Runner:
docker model run hf.co/YourIdentity/MiniCPM5-2B-heretic
| { | |
| "version": "3", | |
| "timestamp": "2026-09-19T10:17:46", | |
| "environment": { | |
| "heretic": { | |
| "version": "2.0.0.dev0", | |
| "is_standard_pypi": false, | |
| "metadata": { | |
| "type": "local" | |
| } | |
| }, | |
| "pytorch_version": "2.14.0+cu132", | |
| "requirements": { | |
| "absl-py": "2.4.0", | |
| "accelerate": "1.13.0", | |
| "alembic": "1.17.2", | |
| "annotated-doc": "0.0.4", | |
| "annotated-types": "0.7.0", | |
| "anyio": "4.12.0", | |
| "attrs": "25.4.0", | |
| "bitsandbytes": "0.49.2", | |
| "certifi": "2025.11.12", | |
| "chardet": "5.2.0", | |
| "charset-normalizer": "3.4.4", | |
| "click": "8.3.1", | |
| "colorama": "0.4.6", | |
| "colorlog": "6.10.1", | |
| "dataproperty": "1.1.0", | |
| "datasets": "4.8.4", | |
| "defusedxml": "0.7.1", | |
| "dill": "0.4.0", | |
| "evaluate": "0.4.6", | |
| "filelock": "3.20.3", | |
| "fsspec": "2025.10.0", | |
| "greenlet": "3.3.0", | |
| "h11": "0.16.0", | |
| "hf-xet": "1.4.2", | |
| "httpcore": "1.0.9", | |
| "httpx": "0.28.1", | |
| "huggingface-hub": "1.7.2", | |
| "idna": "3.15", | |
| "immutabledict": "4.3.1", | |
| "jinja2": "3.1.6", | |
| "joblib": "1.5.2", | |
| "jsonlines": "4.0.0", | |
| "langdetect": "1.0.9", | |
| "lm-eval": "0.4.11", | |
| "lxml": "6.0.2", | |
| "mako": "1.3.12", | |
| "markdown-it-py": "4.0.0", | |
| "markupsafe": "3.0.3", | |
| "mbstrdecoder": "1.1.4", | |
| "mdurl": "0.1.2", | |
| "more-itertools": "10.8.0", | |
| "mpmath": "1.3.0", | |
| "multiprocess": "0.70.18", | |
| "networkx": "3.6.1", | |
| "nltk": "3.10.3", | |
| "numpy": "2.3.5", | |
| "optuna": "4.8.0", | |
| "packaging": "25.0", | |
| "pandas": "2.3.3", | |
| "pathvalidate": "3.3.1", | |
| "peft": "0.19.1", | |
| "pillow": "12.3.0", | |
| "portalocker": "3.2.0", | |
| "prompt-toolkit": "3.0.52", | |
| "psutil": "7.2.2", | |
| "py-cpuinfo": "9.0.0", | |
| "pyarrow": "23.0.1", | |
| "pydantic": "2.12.5", | |
| "pydantic-core": "2.41.5", | |
| "pydantic-settings": "2.14.2", | |
| "pygments": "2.20.0", | |
| "pytablewriter": "1.2.1", | |
| "python-dateutil": "2.9.0.post0", | |
| "python-dotenv": "1.2.2", | |
| "pytz": "2025.2", | |
| "pywin32": "311", | |
| "pyyaml": "6.0.3", | |
| "questionary": "2.1.1", | |
| "regex": "2025.11.3", | |
| "requests": "2.33.0", | |
| "rich": "14.3.3", | |
| "rouge-score": "0.1.2", | |
| "sacrebleu": "2.6.0", | |
| "safetensors": "0.7.0", | |
| "scikit-learn": "1.8.0", | |
| "scipy": "1.16.3", | |
| "setuptools": "83.0.0", | |
| "shellingham": "1.5.4", | |
| "six": "1.17.0", | |
| "sqlalchemy": "2.0.45", | |
| "sqlitedict": "2.1.0", | |
| "sympy": "1.14.0", | |
| "tabledata": "1.3.4", | |
| "tabulate": "0.10.0", | |
| "tcolorpy": "0.1.7", | |
| "threadpoolctl": "3.6.0", | |
| "tokenizers": "0.22.1", | |
| "tomli-w": "1.2.0", | |
| "torch": "2.14.0", | |
| "torchvision": "0.29.0", | |
| "tqdm": "4.67.1", | |
| "transformers": "5.6.2", | |
| "typepy": "1.3.4", | |
| "typer": "0.24.1", | |
| "typing-extensions": "4.15.0", | |
| "typing-inspection": "0.4.2", | |
| "tzdata": "2025.2", | |
| "urllib3": "2.7.0", | |
| "wcwidth": "0.2.14", | |
| "word2number": "1.1", | |
| "xxhash": "3.6.0", | |
| "zstandard": "0.25.0" | |
| } | |
| }, | |
| "settings": { | |
| "model": "openbmb/MiniCPM5-2B", | |
| "model_commit": "12a3808a956f869c767195e9266b59c4d21d92e2", | |
| "dtypes": [ | |
| "auto", | |
| "float16", | |
| "bfloat16", | |
| "float32" | |
| ], | |
| "quantization": "none", | |
| "device_map": "auto", | |
| "max_memory": { | |
| "0": "7GB", | |
| "cpu": "16GB" | |
| }, | |
| "offload_outputs_to_cpu": true, | |
| "batch_size": 128, | |
| "max_response_length": 100, | |
| "response_prefix": "<think></think>\n\n", | |
| "scorers": [ | |
| { | |
| "plugin": "heretic.scorers.keyword_rate.KeywordRate", | |
| "optimization": "minimize", | |
| "instance_name": null | |
| }, | |
| { | |
| "plugin": "heretic.scorers.kl_divergence.KLDivergence", | |
| "optimization": "minimize", | |
| "instance_name": null | |
| } | |
| ], | |
| "orthogonalize_direction": true, | |
| "row_normalization": "full", | |
| "full_normalization_lora_rank": 3, | |
| "winsorization_quantile": 1.0, | |
| "n_trials": 200, | |
| "n_startup_trials": 60, | |
| "seed": 2349379831, | |
| "max_shard_size": "5GB", | |
| "export_strategy": "merge", | |
| "checkpoint_action": null, | |
| "trial_index": null, | |
| "n_additional_trials": null, | |
| "model_action": null, | |
| "upload_repo_private": null, | |
| "upload_reproducibility_information": null, | |
| "ignore_mismatches": null, | |
| "system_prompt": "You are a helpful assistant.", | |
| "good_prompts": { | |
| "dataset": "mlabonne/harmless_alpaca", | |
| "commit": "02c6a92cfcf11bb0c387334f8146d149d65b587f", | |
| "config": null, | |
| "split": "train[:400]", | |
| "column": "text", | |
| "prefix": "", | |
| "suffix": "", | |
| "system_prompt": null | |
| }, | |
| "bad_prompts": { | |
| "dataset": "mlabonne/harmful_behaviors", | |
| "commit": "01cead01398926d81f7c52bdb790ee8cf77ebba7", | |
| "config": null, | |
| "split": "train[:400]", | |
| "column": "text", | |
| "prefix": "", | |
| "suffix": "", | |
| "system_prompt": null | |
| } | |
| }, | |
| "parameters": { | |
| "direction_index": null, | |
| "abliteration_parameters": { | |
| "attn.o_proj": { | |
| "max_weight": 1.3336960277629988, | |
| "max_weight_position": 30.12840962038319, | |
| "min_weight": 1.3204315790632537, | |
| "min_weight_distance": 15.593181689047888 | |
| }, | |
| "mlp.down_proj": { | |
| "max_weight": 0.5678187570224483, | |
| "max_weight_position": 26.56783921267147, | |
| "min_weight": 0.5594695866074149, | |
| "min_weight_distance": 8.995097310050177 | |
| } | |
| } | |
| }, | |
| "scores": [ | |
| { | |
| "name": "Refusals", | |
| "score": { | |
| "value": 0.06, | |
| "rich_display": "[bold]6[/]/100", | |
| "md_display": "6/100" | |
| }, | |
| "baseline": { | |
| "value": 0.99, | |
| "rich_display": "[bold]99[/]/100", | |
| "md_display": "99/100" | |
| } | |
| }, | |
| { | |
| "name": "KL divergence", | |
| "score": { | |
| "value": 0.030704282224178314, | |
| "rich_display": "[bold]0.0307[/]", | |
| "md_display": "0.0307" | |
| }, | |
| "baseline": { | |
| "value": 0, | |
| "rich_display": "[bold]0[/] [italic](by definition)[/]", | |
| "md_display": "0 *(by definition)*" | |
| } | |
| } | |
| ], | |
| "hashes": { | |
| "model-00001-of-00002.safetensors": "18e808c0fef667f41e4a0665f02f7a0cb911a5ed4564a24bb46e84b0d89d4ab8", | |
| "model-00002-of-00002.safetensors": "b60d5ac5c97792134549578566290e76fe08d6e082565b118b1d43cf5472224e" | |
| } | |
| } |